IBM/ACPBench

ACPBench: Reasoning about Action, Change, and Planning. A benchmark designed to evaluate the fundamental reasoning abilities in the domains of action, change, and planning. It spans seven atomic reasoning tasks--determining action applicability, action reachability, plan justification, determining landmark, predicting state transitions, state rea

46
/ 100
Emerging

This project helps evaluate how well AI models understand and reason about real-world tasks involving sequences of actions, changes in environment, and planning. It takes in descriptions of a problem (like moving cars with a ferry) and asks questions about applicable actions, predictable outcomes, or whether a goal is achievable. The output is a performance score for the AI's reasoning abilities. It's designed for AI researchers and developers creating or assessing advanced AI systems.

Use this if you are developing or evaluating large language models or other AI agents that need to perform complex reasoning, planning, and decision-making in dynamic environments.

Not ideal if you are looking for a ready-to-use AI planning system or a tool to solve specific real-world operational problems directly, as this is a benchmark for AI capabilities.

AI-reasoning AI-planning AI-evaluation language-model-benchmarking decision-making-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

32

Forks

5

Language

Python

License

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/IBM/ACPBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.